© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24067
    Prev
    Next
    INDEX
    Explanations

    what you can do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    eps
    -0.10
     Harden
    -0.10
    大象
    -0.09
    æīĢåľ¨çļĦ
    -0.08
    åĪª
    -0.08
    åĪł
    -0.08
    rello
    -0.08
     поÑįÑĤомÑĥ
    -0.08
    çĶ»çĶ»
    -0.08
    gie
    -0.08
    POSITIVE LOGITS
    èį¡
    0.09
    åĩĨå¤ĩ
    0.09
    åĩĨå¤ĩå·¥ä½ľ
    0.09
     rele
    0.09
    fen
    0.09
     absent
    0.09
    åĩĨ
    0.08
    æłĩå¿Ĺ
    0.08
    æĮ¯åħ´
    0.08
    æĿijéĩĮ
    0.08
    Activations Density 0.039%

    No Known Activations